English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper we tackle the problem of estimating the 3D pose of objectinstances, using convolutional neural networks. State of the art methodsusually solve the challenging problem of regression in angle space indirectly,focusing on learning discriminative features that are later fed into a separatearchitecture for 3D pose estimation. In contrast, we propose an end-to-endlearning framework for directly regressing object poses by exploiting SiameseNetworks. For a given image pair, we enforce a similarity measure between therepresentation of the sample images in the feature and pose space respectively,that is shown to boost regression performance. Furthermore, we argue that ourpose-guided feature learning using our Siamese Regression Network generatesmore discriminative features that outperform the state of the art. Last, ourfeature learning formulation provides the ability of learning features that canperform under severe occlusions, demonstrating high performance on our novelhand-object dataset.

Siamese Regression Networks with Efficient mid-level Feature Extraction for 3D Object Pose Estimation